Learning Noise Adapters for Incremental Speech Enhancement

Abstract

Incremental speech enhancement (ISE), with the ability to incrementally adapt to new noise domains, represents a critical yet comparatively under-investigated topic. While the regularization-based method has been proposed to solve the ISE task, it usually suffers from the dilemma wherein the gain of one domain directly entails the loss of another. To solve this issue, we propose an effective paradigm, termed Learning Noise Adapters (LNA), which significantly mitigates the catastrophic domain forgetting phenomenon in the ISE task. In our methodology, we employ a frozen pre-trained model to train and retain a domain-specific adapter for each newly encountered domain, enabling the capture of variations in feature distributions within these domains. Subsequently, our approach involves the development of an unsupervised, training-free noise selector for the inference stage, which is responsible for identifying the domains of test speech samples. A comprehensive experimental validation has substantiated the effectiveness of our approach.